Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4225 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.4478. Min Range: -3.4478

Max Act: 3.1723. Min Act: -0.0000

Data Index: 1623712 (The Pile)

Max Activating Token Index: 410

Text #1

Max Range: 3.4478. Min Range: -3.4478

Max Act: 3.4478. Min Act: -0.0000

Data Index: 634756 (The Pile)

Max Activating Token Index: 283

Text #2

Max Range: 3.4478. Min Range: -3.4478

Max Act: 3.1094. Min Act: -0.0000

Data Index: 878820 (The Pile)

Max Activating Token Index: 110

Text #3

Max Range: 3.4478. Min Range: -3.4478

Max Act: 3.0731. Min Act: -0.0000

Data Index: 1003234 (The Pile)

Max Activating Token Index: 688

Text #4

Max Range: 3.4478. Min Range: -3.4478

Max Act: 3.1928. Min Act: -0.0000

Data Index: 1679355 (The Pile)

Max Activating Token Index: 78

Text #5

Max Range: 3.4478. Min Range: -3.4478

Max Act: 3.0237. Min Act: -0.0000

Data Index: 171643 (The Pile)

Max Activating Token Index: 258

Text #6

Max Range: 3.4478. Min Range: -3.4478

Max Act: 2.8254. Min Act: -0.0000

Data Index: 252309 (The Pile)

Max Activating Token Index: 871

Text #7

Max Range: 3.4478. Min Range: -3.4478

Max Act: 2.9186. Min Act: -0.0000

Data Index: 1763204 (The Pile)

Max Activating Token Index: 245

Text #8

Max Range: 3.4478. Min Range: -3.4478

Max Act: 2.8984. Min Act: -0.0000

Data Index: 390331 (The Pile)

Max Activating Token Index: 74

Text #9

Max Range: 3.4478. Min Range: -3.4478

Max Act: 2.6810. Min Act: -0.0000

Data Index: 192246 (The Pile)

Max Activating Token Index: 52

Text #10

Max Range: 3.4478. Min Range: -3.4478

Max Act: 3.0719. Min Act: -0.0000

Data Index: 1286314 (The Pile)

Max Activating Token Index: 284

Text #11

Max Range: 3.4478. Min Range: -3.4478

Max Act: 2.9620. Min Act: -0.0000

Data Index: 154217 (The Pile)

Max Activating Token Index: 208

Text #12

Max Range: 3.4478. Min Range: -3.4478

Max Act: 3.0089. Min Act: -0.0000

Data Index: 1135378 (The Pile)

Max Activating Token Index: 779

Text #13

Max Range: 3.4478. Min Range: -3.4478

Max Act: 2.7423. Min Act: -0.0000

Data Index: 1370705 (The Pile)

Max Activating Token Index: 130

Text #14

Max Range: 3.4478. Min Range: -3.4478

Max Act: 2.8873. Min Act: -0.0000

Data Index: 1397722 (The Pile)

Max Activating Token Index: 74

Text #15

Max Range: 3.4478. Min Range: -3.4478

Max Act: 2.7303. Min Act: -0.0000

Data Index: 506254 (The Pile)

Max Activating Token Index: 242

Text #16

Max Range: 3.4478. Min Range: -3.4478

Max Act: 2.6225. Min Act: -0.0000

Data Index: 1477515 (The Pile)

Max Activating Token Index: 95

Text #17

Max Range: 3.4478. Min Range: -3.4478

Max Act: 2.8761. Min Act: -0.0000

Data Index: 309501 (The Pile)

Max Activating Token Index: 214

Text #18

Max Range: 3.4478. Min Range: -3.4478

Max Act: 2.8599. Min Act: -0.0000

Data Index: 803366 (The Pile)

Max Activating Token Index: 175

Text #19

Max Range: 3.4478. Min Range: -3.4478

Max Act: 2.6886. Min Act: -0.0000

Data Index: 1631124 (The Pile)

Max Activating Token Index: 616